Skip to content

feat: CUDA port of TurboQuant3 KV cache — 3.47x compression, 98.5% of F16 decode speed on RTX 5090 #3

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
signalnine wants to merge 13 commits into
base: feature/turboquant-kv-cache
Choose a base branch
from

perf: sparse V dequant — skip negligible attention weights in VEC kernel

a5efe54
Select commit
Loading
Failed to load commit list.
Sign in for the full log view
Open

feat: CUDA port of TurboQuant3 KV cache — 3.47x compression, 98.5% of F16 decode speed on RTX 5090 #3

perf: sparse V dequant — skip negligible attention weights in VEC kernel
a5efe54
Select commit
Loading
Failed to load commit list.
labeler
succeeded Mar 28, 2026 in 12s